© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 252721
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ロシア
    0.55
     malaysia
    0.49
     러시아
    0.48
    は何
    0.46
    า
    0.46
     española
    0.46
    をした
    0.46
     polymerase
    0.45
     म्यूचुअल
    0.44
     catalyst
    0.44
    POSITIVE LOGITS
    buds
    0.49
    їз
    0.46
    udh
    0.46
     fullness
    0.46
    ns
    0.46
     நிறுவ
    0.45
    kup
    0.45
    nels
    0.45
    㻐
    0.45
    zí
    0.45
    Activations Density 0.001%

    No Known Activations